{"id":"W2747730426","doi":"10.1109/iccvw.2017.319","title":"STNet: Selective Tuning of Convolutional Networks for Object Localization","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Convolutional neural network; Benchmark (surveying); Abstraction; Artificial intelligence; Representation (politics); Covert; Class (philosophy); Feed forward; Visual processing; Machine learning; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006962791,0.001342981,0.0005613746,0.0005410469,0.0002939916,0.0005911151,0.001893629,0.0009236918,0.002492681],"category_scores_gemma":[0.002452906,0.0003868699,0.0004900988,0.0005243967,0.000578868,0.001364909,0.001314481,0.001268532,0.0008557136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007811163,"about_ca_system_score_gemma":0.0008301293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004405336,"about_ca_topic_score_gemma":0.008304987,"domain_scores_codex":[0.9996871,0.00005594669,0.00001462578,0.0001157714,0.00007585868,0.00005063105],"domain_scores_gemma":[0.9995785,0.0001634347,0.00005402754,0.0001001334,0.00006679233,0.0000370595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003773254,0.0002735356,0.002853462,0.0003084593,0.0002484852,0.0002217325,0.0001131318,0.4561993,0.06756713,0.01096826,0.01527969,0.4455895],"study_design_scores_gemma":[0.00002733526,0.00006645329,0.0004013401,0.00001051701,0.0000210063,0.00004000851,0.000008590298,0.9754608,0.01546908,0.00627604,0.002209246,0.000009573258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09218189,0.001562459,0.8824365,0.000363106,0.0002276338,0.0001509917,0.0005671213,0.01663262,0.005877666],"genre_scores_gemma":[0.7802044,0.0005304586,0.2122955,0.0004223466,0.0001082456,0.0002475699,0.001159657,0.0009856543,0.004046103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004405336,"threshold_uncertainty_score":0.008759439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03293558144974192,"score_gpt":0.3061961249415887,"score_spread":0.2732605434918468,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}